Model save

README.md

@@ -31,13 +31,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.051110418843398e-06
-- train_batch_size: 32
+- learning_rate: 5.61151641533451e-06
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 5
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec6c54a55b2c392cf8999e00d8ec54daa9c4c6bb07c8c790a0261ab616c6d42
+oid sha256:5efc55b36f4bd23118f8c269422e95f803a72387f5fe7ad2c8f2a93ef84e2ffa
 size 498612824

run-e3fe7_00000/checkpoint-10/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "allenai/biomed_roberta_base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-e3fe7_00000/checkpoint-10/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efc55b36f4bd23118f8c269422e95f803a72387f5fe7ad2c8f2a93ef84e2ffa
+size 498612824

run-e3fe7_00000/checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80217c5db9a269a838e6e4d5bec8e5ba714cc9e37a2747bd565a0051d7082b5b
+size 997345530

run-e3fe7_00000/checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780c0ed7bfb2fb6b91d2b65dd90dff344ec5cfbd0c40aeb6888c6c5271f0e443
+size 14244

run-e3fe7_00000/checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d6ebb52df40a83b49e69f4f0cad47ac8a6628abd3f42fdf4dd8c9d7777cb49
+size 1064

run-e3fe7_00000/checkpoint-10/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-e3fe7_00000/checkpoint-10/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "padding": true,
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "truncation": true,
+  "unk_token": "<unk>"
+}

run-e3fe7_00000/checkpoint-10/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.6982510685920715,
+  "best_model_checkpoint": "Mach_0_tuning/run-e3fe7_00000/checkpoint-10",
+  "epoch": 2.0,
+  "eval_steps": 1,
+  "global_step": 10,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.6984328031539917,
+      "eval_runtime": 1.9469,
+      "eval_samples_per_second": 10.273,
+      "eval_steps_per_second": 1.541,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.6982510685920715,
+      "eval_runtime": 1.9741,
+      "eval_samples_per_second": 10.131,
+      "eval_steps_per_second": 1.52,
+      "step": 10
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 25,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.61151641533451e-06,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.07969454818643928
+  }
+}

run-e3fe7_00000/checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30468ce969364f2cc330f49080e67955cdc0765511a9774d6abe69104c474058
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126c9f70aefb0701137e9565276d3e58fb48da6a86480a784dd29d58625eeea2
-size 4536
+oid sha256:30468ce969364f2cc330f49080e67955cdc0765511a9774d6abe69104c474058
+size 4600